Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, it discloses permission rules, the requirement that added concepts already exist on the map, loop prevention, and that the reason is retained with the record. These details are important for a destructive, open-world mutation and are not contradicted by the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loads the action and resource. The phrase 'one-line reason the record keeps' is slightly awkward, but overall it is dense and purposeful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex destructive mutation, it provides good permission and precondition context. However, with six parameters and no schema descriptions, the unexplained `task` parameter and strength values mean the definition is not fully complete for safe invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description carries a heavy burden. It maps the add/remove/soften actions and the reason field, and adds constraints for adding, but it does not explain the `task` parameter or the `hard`/`soft` strength enum, leaving important call semantics to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses specific verbs (add, remove, soften) and a clear resource (what a concept on the ai.page map builds on). This is a distinct operation from read/propose/versioning siblings and can be understood without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explains who may add a need and who may remove one, including the condition that learners' results doubt the dependency. It lacks explicit mention of alternative tools or when not to use this one, but the operational conditions are clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.